# Training with Exploration Improves a Greedy Stack-LSTM Parser

arXiv: https://arxiv.org/abs/1603.03793 · HTML: https://mlsanity.com/paper/1603.03793/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2016.

## Built on by (most cited first, 4 of 4)

- [Inducing and Using Alignments for Transition-based AMR Parsing](https://mlsanity.com/paper/2205.01464/) (2022)
- [Transformers as Graph-to-Graph Models](https://mlsanity.com/paper/2310.17936/) (2023)
- [Dependency Parsing with Backtracking using Deep Reinforcement Learning](https://mlsanity.com/paper/2206.13914/) (2022)
- [Alleviate Exposure Bias in Sequence Prediction  with Recurrent Neural Networks](https://mlsanity.com/paper/2103.11603/) (2021)

## Abstract (arXiv)

We adapt the greedy Stack-LSTM dependency parser of Dyer et al. (2015) to support a training-with-exploration procedure using dynamic oracles(Goldberg and Nivre, 2013) instead of cross-entropy minimization. This form of training, which accounts for model predictions at training time rather than assuming an error-free action history, improves parsing accuracies for both English and Chinese, obtaining very strong results for both languages. We discuss some modifications needed in order to get training with exploration to work well for a probabilistic neural-network.